From 7a03280df4555998fc99399907062b62383db2c4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com>
Date: Thu, 30 Apr 2015 21:31:38 +0600
Subject: [PATCH] [vporn] More metadata extraction fixes and tests update
(#5560)
---
youtube_dl/extractor/vporn.py | 10 ++--------
1 file changed, 2 insertions(+), 8 deletions(-)
diff --git a/youtube_dl/extractor/vporn.py b/youtube_dl/extractor/vporn.py
index 04ed0b381..92c90e517 100644
--- a/youtube_dl/extractor/vporn.py
+++ b/youtube_dl/extractor/vporn.py
@@ -27,9 +27,6 @@ class VpornIE(InfoExtractor):
'duration': 393,
'age_limit': 18,
'view_count': int,
- 'like_count': int,
- 'dislike_count': int,
- 'comment_count': int,
}
},
{
@@ -47,9 +44,6 @@ class VpornIE(InfoExtractor):
'duration': 588,
'age_limit': 18,
'view_count': int,
- 'like_count': int,
- 'dislike_count': int,
- 'comment_count': int,
}
},
]
@@ -72,10 +66,10 @@ class VpornIE(InfoExtractor):
thumbnail = 'http://www.vporn.com' + thumbnail
uploader = self._html_search_regex(
- r'(?s)Uploaded by:.*?<a href="/user/[^"]+">([^<]+)</a>',
+ r'(?s)Uploaded by:.*?<a href="/user/[^"]+"[^>]*>(.+?)</a>',
webpage, 'uploader', fatal=False)
- categories = re.findall(r'<a href="/cat/[^"]+">([^<]+)</a>', webpage)
+ categories = re.findall(r'<a href="/cat/[^"]+"[^>]*>([^<]+)</a>', webpage)
duration = parse_duration(self._search_regex(
r'Runtime:\s*</span>\s*(\d+ min \d+ sec)',